用于电弧检测的电力专用SoC设计

针对传统的电弧电路故障检测结果不准确的问题,设计用于电弧检测的SoC系统,并且在55nm工艺下进行流片验证。采用包含两种结构的模数转换器的片上电压源,设计了锁相环以及复位电路,精度最高可达8.67 bit。验证结果表明,本设计可提高电弧检测的准确性。     

Machine learning algorithm selection for windage alteration fault diagnosis of mine ventilation system

Machine learning algorithms have been widely used in mine fault diagnosis. The correct selection of the suitable algorithms is the key factor that affects the fault diagnosis. However, the impact of machine learning algorithms on the prediction performance of mine fault diagnosis models has not been fully evaluated. In this study, the windage alteration faults (WAFs) diagnosis models, which are based on K-nearest neighbor algorithm (KNN), multi-layer perceptron (MLP), support vector machine (SVM), and decision tree (DT), are constructed. Furthermore, the applicability of these four algorithms in the WAFs diagnosis is explored by a T-type ventilation network simulation experiment and the field empirical application research of Jinchuan No. 2 mine. The accuracy of the fault location diagnosis for the four models in both networks was 100%. In the simulation experiment, the mean absolute percentage error (MAPE) between the predicted values and the real values of the fault volume of the four models was 0.59%, 97.26%, 123.61%, and 8.78%, respectively. The MAPE for the field empirical application was 3.94%, 52.40%, 25.25%, and 7.15%, respectively. The results of the comprehensive evaluation of the fault location and fault volume diagnosis tests showed that the KNN model is the most suitable algorithm for the WAFs diagnosis, whereas the prediction performance of the DT model was the second-best. This study realizes the intelligent diagnosis of WAFs, and provides technical support for the realization of intelligent ventilation.     

Enhanced wide-activated residual network for efficient and accurate image deblocking

To save bandwidth and storage space as well as speed up data transmission, people usually perform lossy compression on images. Although the JPEG standard is a simple and effective compression method, it usually introduces various visually unpleasing artifacts, especially the notorious blocking artifacts. In recent years, deep convolutional neural networks (CNNs) have seen remarkable development in compression artifacts reduction. Despite the excellent performance, most deep CNNs suffer from heavy computation due to very deep and wide architectures. In this paper, we propose an enhanced wide-activated residual network (EWARN) for efficient and accurate image deblocking. Specifically, we propose an enhanced wide-activated residual block (EWARB) as basic construction module. Our EWARB gives rise to larger activation width, better use of interdependencies among channels, and more informative and discriminative non-linearity activation features without more parameters than residual block (RB) and wide-activated residual block (WARB). Furthermore, we introduce an overlapping patches extraction and combination (OPEC) strategy into our network in a full convolution way, leading to large receptive field, enforced compatibility among adjacent blocks, and efficient deblocking. Extensive experiments demonstrate that our EWARN outperforms several state-of-the-art methods quantitatively and qualitatively with relatively small model size and less running time, achieving a good trade-off between performance and complexity.     

Hydraulic reactivity and cement formation of baghdadite

In this study, the hydraulic reactivity and cement formation of baghdadite (Ca₃ZrSi₂O₉) was investigated. The material was synthesized by sintering a mixture of CaCO₃, SiO₂, and ZrO₂ and then mechanically activated using a planetary mill. This leads to a decrease in particle and crystallite size and a partial amorphization of baghdadite as shown by X-ray powder diffraction (XRD) and laser diffraction measurements. Baghdadite cements were formed by the addition of water at a powder to liquid ratio of 2.0 g/ml. Maximum compressive strengths were found to be ~2 MPa after 3-day setting for a 24-h ground material. Inductively coupled plasma mass spectrometry (ICP-MS) measurements showed an incongruent dissolution profile of set cements with a preferred dissolution of calcium and only marginal release of zirconium ions. Cement formation occurs under alkaline conditions, whereas the unground raw powder leads to a pH of 11.9 during setting, while prolonged grinding increased pH values to approximately 12.3.     

基于PBFT区块链技术的电网企业仓储系统

提出了一种基于实用拜占庭容错(PBFT)算法的区块链技术,首先对传统的实用拜占庭容错算法原理进行了阐述,该传统算法包含前期、需求、预准备、准备、确认、答复6个阶段,但传统算法具有实时性差、缺乏惩罚机制、带宽高的缺点。针对出现的这些问题,又对传统算法进行了改进,具体涉及记账节点、共识过程以及视图切换过程。通过测试进一步证明了该改进算法的实用性,并将该算法应用于电网企业中,构建的虚拟仓库实现了联储联备,降低了库存资金的耗费,并且提高了电网企业库存管理的效率。     

基于残差决策的自动飞行控制系统远程实时故障诊断

针对自动飞行控制系统结构复杂、关联部件众多,发生故障时诊断时间长,从而影响飞机运行效率的问题,提出一种基于飞机通信寻址报告系统(ACARS)的远程实时故障诊断方案。首先,分析自动飞行控制系统的故障特点,设计搭建检测滤波器;然后,利用ACARS数据链实时发送的自动飞行控制系统的关键信息进行相关部件的残差计算,并根据残差决策算法进行故障诊断及定位;最后,针对不同故障部件残差间的差异大、决策门限无法统一的缺点,提出基于二次差值的残差决策改进算法,减缓了检测对象的整体变化趋势,降低了随机噪声和干扰的影响,避免了将瞬态故障诊断为系统故障的情况。实验仿真结果表明,基于二次差值的改进残差决策算法避免了多决策门限的复杂性,在采样时间为0.1 s的情况下,故障检测所需时间大约为2 s,故障检测时间大幅降低,有效故障检测率大于90%。     

基于深度信念网络的列车故障音频诊断方法

铁路在交通运输行业有着举足轻重的地位，一旦列车发生故障将会导致严重的生命财产损失。由于列车发生故障的概率相对较低，因此难以捕获列车的故障样本。针对上述问题，提出了一种无监督学习的列车故障识别方法，通过检测列车音频信号来识别列车故障。该方法基于深度信念网络(DBN)，利用小波包分解提取检测信号的特征向量并将其作为DBN的输入，待网络充分训练后，由训练好的DBN识别当前列车的运行状况。现场监测实验结果表明，该方法能够在无监督的条件下有效识别列车故障，保障了列车的运行安全。     

胡萝卜丁中维生素C在热风辅助射频干燥过程中降解的动力学模型

目的研究热风辅助射频(hot air-assisted radio frequency,HA-RF)干燥过程中维生素C随温度变化的降解动力学模型。方法在6.5 cm极板间距和60℃热风系统条件下进行HA-RF干燥,重点研究胡萝卜丁中维生素C在干燥过程中的降解动力学,包括脱氢抗坏血酸(dehydroascorbic acid,DHAA)和抗坏血酸(ascorbic acid,AA)。总维生素C含量采用2,4-硝基苯肼分光光度法测定,AA采用2,6-二氯吲哚酚滴定法测定。结果HA-RF干燥过程中维生素C的降解规律符合一级可逆模型,其降解活化能为40.54 kJ/mol。DHAA活化能为35.83 kJ/mol,表明DHAA的稳定性低于AA。结论本研究使用的干燥温度为62.5~77.5℃,较高的干燥温度下维生素C降解速率较高,较低处理温度下的降解过程具有更好的模型适应度(R2>0.98)。     

高校实验室计算机网络故障诊断技术研究

为了提升高校实验数据处理水平,高校实验室的相关建设工作已经步入正轨,但层出不穷的信息安全问题也向高校实验室计算机网络维护工作提出了新的挑战。文章从现阶段高校实验室计算机网络的相关建设工作出发,简要论述引发网络故障的具体原因,并对其诊断技术进行探讨。     

Preparation of α-cordierite through mechanochemical activation of MgO–Al2O3–SiO2 ternary system

Samples of the ternary system MgO–Al₂O₃–SiO₂ with stoichiometric composition in relation to α-cordierite (Mg₂A_l4Si₅O₁₈), consisting of 22.2 mol% MgO, 22.2 mol% Al₂O₃, and 55.6 mol% SiO₂, were activated in a low energy mill with a constant speed of 100 rpm, in an aqueous medium. The precursors used were corundum (Al₂O₃), silica gel HF254 type 60 (SiO₂), and periclase (MgO). The objective of the present study was to evaluate the effect of mechanochemical activation on the solid-state synthesis of α-cordierite, using a low energy ball mill. Another objective was to shed light on the effect of mechanochemical activation on the steps of α-cordierite formation. For this end several grinding conditions were evaluated, varying the time and mass ratio of precursors/grinding elements, as well as calcination at different temperatures between 950 °C and 1350 °C for 2 h. The samples were analyzed for the determination of the formed phases by Infrared (IR) and X-ray Diffraction (XRD). The phases identified in uncalcined samples were brucite (Mg(OH)₂), forsterite (Mg₂SiO₄), enstatite (MgSiO₃), spinel (MgAl₂O₃), amorphous silica (SiO₂), corundum (α-Al₂O₃), and zirconia (monoclinic and tetragonal ZrO₂). The lowest temperature corresponding to the formation of α-cordierite (α-Mg₂Al₄Si₅O₁₈) was 1150 °C and a considerable amount of this phase (16.2%) was observed at this temperature, for the sample with the higher mechanochemical activation. In a solid-state reaction, α-cordierite is normally obtained at around 1400 °C, therefore, the formation of this phase at 1150 °C confirms that the mechanochemical activation method, using a low-cost ball mill, is efficient in reducing the solid-state reaction temperature.